Opportunistic measurements and processing of user's context

• US 10,201,312 B2
• Filed: 12/08/2014
• Issued: 02/12/2019
• Est. Priority Date: 12/08/2014
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Kumar, Arvind, Ahmad, Marisa A.
• Primary Examiner(s): Patel, Niketa
• Assistant Examiner(s): BALDWIN, NATHAN AARON
• Application Number:
  US14/563,809
• Publication Number:
  US 20160157782A1
• Time in Patent Office: 1,527 Days
• CPC Class Codes: A61B 2560/0462 Apparatus with built-in sensors
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/02 Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/6897 Computer input devices, e.g. mice or keyboards
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Embodiments of the present disclosure provide techniques and configurations for an apparatus for opportunistic measurements and processing of user'"'"'s context. In one instance, the apparatus may include a sensor module with sensors disposed on a work surface to maintain direct or indirect contact with portions of user'"'"'s limbs for a time period when the portions of user'"'"'s limbs are disposed on the work surface, to obtain readings of first and second parameters of user'"'"'s context over the time period of the direct or indirect contact; and a processing module to process the readings of the first and second parameters, including to identify a first feature of the first parameter and a second feature of the second parameter that is temporally correlated with the first feature, and determine a third parameter of the user'"'"'s context based on the identified first and second features. Other embodiments may be described and/or claimed.

Claims

1. An apparatus, comprising:

a work surface, including at least portions of one of;

a keyboard, a bezel, or a back side of the apparatus, wherein the apparatus comprises one of a tablet computer or a smartphone;

a plurality of sensors mounted on the portions of the work surface, adapted to maintain a contact with portions of user'"'"'s limbs that are in contact or interact with the work surface in a process of interaction of the user'"'"'s limbs with the apparatus, wherein the plurality of sensors include two or more electrodes to obtain readings of electrocardiographic (ECG) data, one or more optical sensors to provide photoplethysmographic (PPG) data, and one or more motion sensors to provide jitter data associated with the user, wherein the jitter data includes indications of a motion of the user'"'"'s limbs in relation to the work surface of the apparatus; and

a processing circuitry coupled with the plurality of sensors, wherein the processing circuitry includes a processor and a memory having instructions that, in response to execution by the processor, is to collect and process the readings of the ECG, PPG, and jitter data provided by respective ones of the plurality of sensors, wherein to process includes to;

collect a set of values from the ECG and PPG readings, including at least readings that indicate a pulse transit time, an amplitude of a PPG curve of the PPG data, and upward and downward slopes of the PPG curve;

determine blood pressure of the user from an empirical correlation between the pulse transit time, the amplitude of the PPG curve, and the upward and downward slopes of the PPG curve;

determine boundary values for the blood pressure of the user, by applying a logistic regression model to the set of values, wherein the boundary values indicate a normal state of the user, wherein to determine boundary values includes to adjust the boundary values over a time period using the jitter data, wherein the jitter data below a threshold is to provide ground truth data for determination of the boundary values; and

provide an indication of a probability of the user being in the normal state, including render for display on a display of the apparatus a notification of the normal state.

2. The apparatus of claim 1, wherein the ECG data includes an interval measured from a beginning of a P-wave to a peak of an S-wave of a QRS complex of the ECG data, the upward slope of the PPG curve comprises a slope between lowest and highest points in the PPG curve, the amplitude of the PPG curve comprises a peak in the curve, and the downward slope of the PPG curve comprises a slope between the highest point and a beginning of a next PPG curve.

3. The apparatus of claim 1, wherein the blood pressure comprises systolic blood pressure (SBP) data and diastolic blood pressure (DBP) data, wherein the processing circuitry is to derive the SBP data and the DBP data from application of a machine-learning algorithm to the ECG and PPG data.

4. The apparatus of claim 1, wherein the one or more motion sensors comprise at least a selected one of:

a gyroscope or accelerometer.

5. The apparatus of claim 1, wherein the one or more optical sensors comprise at least one of a light emitting diode (LED) and photodetector.

6. The apparatus of claim 1, wherein the apparatus is a computing device, wherein the portions of the user'"'"'s limbs include at least one of:

wrists, palms, or hands that are disposed on the work surface to interact with the apparatus.

7. An apparatus, comprising:

a casing, having at least one work surface that includes a plurality of sensors disposed on the work surface adapted to maintain contact with portions of a user'"'"'s limbs that are in contact or interact with the work surface, to obtain readings of electrocardiographic (ECG) data, photoplethysmographic (PPG) data, and jitter data associated with the user, wherein the work surface of the casing includes at least portions of one of;

a keyboard, a bezel, or a back side of the apparatus, wherein the apparatus comprises one of a tablet computer or a smartphone, wherein the plurality of sensors include two or more electrodes to obtain the readings of ECG data, one or more optical sensors to provide the PPG data, and one or more motion sensors to provide the jitter data;

a processor communicatively coupled with the plurality of sensors; and

a memory coupled with the processor and having instructions which, in response to execution by the processor, is to collect and process the readings of the ECG, PPG, and jitter data provided by the respective of the plurality of sensors, wherein to process includes to;

access a set of values from the ECG and PPG readings, including at least readings that indicate a pulse transit time, an amplitude of a PPG curve of the PPG data, and upward and downward slopes of the PPG curve;

determine blood pressure of the user from an empirical correlation between the pulse transit time, the amplitude of the PPG curve, and the upward and downward slopes of the PPG curve;

determine boundary values for the blood pressure of the user, by applying a logistic regression model to the set of values, wherein the boundary values indicate a normal state of the user, wherein to determine boundary values includes to adjust the boundary values over a time period using the jitter data, wherein the jitter data below a threshold is to provide ground truth data for determination of the boundary values; and

provide an indication of a probability of the user being in the normal state, including output for display on a display of the apparatus a notification of the normal state.

8. The apparatus of claim 7, further comprising a sensor aggregator coupled with the plurality of sensors, to power on the plurality of sensors and to pre-process the readings provided by the plurality of sensors.

9. The apparatus of claim 8, wherein the sensor aggregator, the processor, and the memory are integrated on a system on chip (SOC), wherein the apparatus further comprises one of:

a laptop computer or a desktop computer.

10. A computer-implemented method, comprising:

obtaining, by a computing device, from a plurality of sensors disposed on a work surface of the computing device that comprises one of a tablet computer or a smartphone, readings of electrocardiographic (ECG) data, photoplethysmographic (PPG) data, and jitter data associated with a user, in response to a contact between portions of the user'"'"'s limbs and the plurality of sensors, wherein the work surface includes at least portions of one of;

a keyboard, a bezel, or a back side of an apparatus, wherein the plurality of sensors include two or more electrodes to obtain the readings of ECG data, one or more optical sensors to provide PPG data, and one or more motion sensors to provide jitter data, wherein obtaining includes collecting, by the computing device, a set of values from the ECG and PPG readings, including at least readings that indicate a pulse transit time, an amplitude of a PPG curve of the PPG data, and upward and downward slopes of the PPG curve;

identifying, by the computing device, blood pressure of the user, from an empirical correlation between the pulse transit time, the amplitude of the PPG curve, and the upward and downward slopes of the PPG curve;

determining, by the computing device, boundary values for the blood pressure of the user, wherein the boundary values indicate a normal state of the user;

wherein determining includes;

applying, by the computing device, a logistic regression model to the set of values, wherein the boundary values indicate a normal state of the user; and

adjusting, by the computing device, the boundary values over a time period using the jitter data, wherein the jitter data below a threshold is to provide ground truth data for determining the boundary values; and

providing, by the computing device, an indication of a probability of the user being in the normal state, including outputting a notification of the normal state on a display of the computing device.

11. The computer-implemented method of claim 10, wherein the ECG data includes an interval measured from a beginning of a wave to a peak of the wave of a QRS complex of the ECG data, the upward slope of the PPG curve comprises a slope between lowest and highest points in the PPG curve, the amplitude of the PPG curve comprises a peak in the curve, and the downward slope of the PPG curve comprises a slope between the highest point and a beginning of a next PPG curve.

12. One or more non-transitory computing device-readable media having executable instructions stored thereon that, in response to execution, cause a computing device to:

obtain, from a plurality of sensors disposed on a work surface of the computing device that comprises one of a tablet computer or a smartphone, readings of electrocardiographic (ECG) data, photoplethysmographic (PPG) data, and jitter data associated with a user, in response to a contact between portions of the user'"'"'s limbs and the plurality of sensors, wherein the work surface includes at least portions of one of;

a keyboard, a bezel, or a back side of the computing device, wherein the plurality of sensors include two or more electrodes to obtain the readings of ECG data, one or more optical sensors to provide PPG data, and one or more motion sensors to provide jitter data, wherein to obtain includes to collect a set of values from the ECG and PPG readings, including at least readings that indicate a pulse transit time, an amplitude of a PPG curve of the PPG data, and upward and downward slopes of the PPG curve;

identify blood pressure of the user, from an empirical correlation between the pulse transit time, the amplitude of the PPG curve, and the upward and downward slopes of the PPG curve;

determine boundary values for the blood pressure of the user, wherein the boundary values indicate a normal state of the user, wherein to determine includes to;

apply a logistic regression model to the collected set of values, wherein the boundary values indicate a normal state of the user; and

adjust the boundary values over a time period using the jitter data, wherein the jitter data below a threshold is to provide ground truth data for determining the boundary values; and

provide an indication of a probability of the user being in the normal state, including render for display on a display of the computing device a notification of the normal state.

13. The non-transitory computing device-readable media of claim 12, wherein the ECG data includes an interval measured from a beginning of a wave to a peak of the wave of a QRS complex of the ECG data, the upward slope of the PPG curve comprises a slope between lowest and highest points in the PPG curve.